How Deep is your Learning: the DL-HARD Annotated Deep Learning Dataset
This provides a new resource for researchers working on neural ranking methods, though it is incremental as it extends an existing dataset.
The authors introduced DL-HARD, an annotated dataset for evaluating neural ranking models on complex topics, building on TREC Deep Learning topics with additional metadata. Experiments showed substantial differences in metrics and system rankings compared to the original benchmark.
Deep Learning Hard (DL-HARD) is a new annotated dataset designed to more effectively evaluate neural ranking models on complex topics. It builds on TREC Deep Learning (DL) topics by extensively annotating them with question intent categories, answer types, wikified entities, topic categories, and result type metadata from a commercial web search engine. Based on this data, we introduce a framework for identifying challenging queries. DL-HARD contains fifty topics from the official DL 2019/2020 evaluation benchmark, half of which are newly and independently assessed. We perform experiments using the official submitted runs to DL on DL-HARD and find substantial differences in metrics and the ranking of participating systems. Overall, DL-HARD is a new resource that promotes research on neural ranking methods by focusing on challenging and complex topics.